db-referential-integrity

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute a local vendor-provided script located at scripts/parse-schema.mjs for the purpose of parsing database DDL.
  • [DATA_EXPOSURE]: The skill performs read-only SQL queries against database system catalogs (such as pg_constraint) to audit foreign key constraints, utilizing the $DATABASE_URL environment variable.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes database schema definitions and query results which are external data sources. 1. Ingestion points: Database DDL files and output from pg_constraint queries. 2. Boundary markers: No specific delimiters are identified to separate ingested data from the agent's instructions. 3. Capability inventory: The skill has access to shell execution (Bash), file system operations (Read, Glob), and database connectivity. 4. Sanitization: No explicit sanitization or validation of the schema content is mentioned before it is processed by the parsing script.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 10:02 PM
Security Audit — agent-trust-hub — db-referential-integrity